Ecosyste.ms: Awesome

An open API service indexing awesome lists of open source software.

Awesome Lists | Featured Topics | Projects

https://github.com/captain1986/captainblackboard

船长关于机器学习、计算机视觉和工程技术的总结和分享
https://github.com/captain1986/captainblackboard

computer-vision convolutional-neural-networks deep-learning optimization-algorithms summary

Last synced: 14 days ago
JSON representation

船长关于机器学习、计算机视觉和工程技术的总结和分享

Host: GitHub
URL: https://github.com/captain1986/captainblackboard
Owner: Captain1986
License: mit
Created: 2019-01-29T11:58:12.000Z (almost 6 years ago)
Default Branch: master
Last Pushed: 2023-04-28T07:37:48.000Z (over 1 year ago)
Last Synced: 2024-10-21T11:38:21.350Z (23 days ago)
Topics: computer-vision, convolutional-neural-networks, deep-learning, optimization-algorithms, summary
Language: C++
Homepage:
Size: 105 MB
Stars: 1,200
Watchers: 39
Forks: 196
Open Issues: 88
Metadata Files:
- Readme: README.md
- License: LICENSE

Awesome Lists containing this project

README

# 船长黑板报

本黑板报专门记录一些船长在工作学习中的一些心得体会

欢迎各路朋友提Pull Request，或者拍砖、改错别字都欢迎～

## 招聘

本人所在阿里淘系技术部常年招数据挖掘/CV/NLP人才，社招校招实习P5~P9欢迎准备好简历找我**内推**，[email protected]

## 目录（注：列且仅列已经完成的，点击可直达）

[D#0001-undefined_reference_to_XXX](https://github.com/Captain1986/CaptainBlackboard/blob/master/D%230001-undefined_reference_to_XXX/D%230001.md)

[D#0002-hack_your_printf](https://github.com/Captain1986/CaptainBlackboard/blob/master/D%230002-hack_your_printf/D%230002.md)

[D#0003-optimizing_cosine_distance_searching_in_a_million_feature-set](https://github.com/Captain1986/CaptainBlackboard/blob/master/D%230003-optimizing_cosine_distance_searching_in_a_million_feature-set/D%230003.md)

[D#0004-depthwise_separable_convolutions_in_mobilenet](https://github.com/Captain1986/CaptainBlackboard/blob/master/D%230004-depthwise_separable_convolutions_in_mobilenet/D%230004.md)

[D#0005-separable_convolutions_in_image_processing](https://github.com/Captain1986/CaptainBlackboard/blob/master/D%230005-separable_convolutions_in_image_processing/D%230005.md)

[D#0006-protect_my_function](https://github.com/Captain1986/CaptainBlackboard/blob/master/D%230006-protect_my_function/D%230006.md)

[D#0007-compile_git_commit_sha1_into_elf](https://github.com/Captain1986/CaptainBlackboard/blob/master/D%230007-compile_git_commit_sha1_into_elf/D%230007.md)

[D#0008-拉格朗日乘子法](https://github.com/Captain1986/CaptainBlackboard/blob/master/D%230008-%E6%8B%89%E6%A0%BC%E6%9C%97%E6%97%A5%E4%B9%98%E5%AD%90%E6%B3%95/D%230008.md)

[D#0009-SVM](https://github.com/Captain1986/CaptainBlackboard/blob/master/D%230009-SVM/D%230009.md)

[D#0010-从线性回归到对率回归到Softmax激活函数](https://github.com/Captain1986/CaptainBlackboard/blob/master/D%230010-%E4%BB%8E%E7%BA%BF%E6%80%A7%E5%9B%9E%E5%BD%92%E5%88%B0%E5%AF%B9%E7%8E%87%E5%9B%9E%E5%BD%92%E5%88%B0Softmax%E6%BF%80%E6%B4%BB%E5%87%BD%E6%95%B0/D%230010.md)

[D#0011-kNN](https://github.com/Captain1986/CaptainBlackboard/blob/master/D%230011-kNN/D%230011.md)

[D#0012-为什么选交叉熵作为分类问题的损失函数](https://github.com/Captain1986/CaptainBlackboard/blob/master/D%230012-%E4%B8%BA%E4%BB%80%E4%B9%88%E9%80%89%E4%BA%A4%E5%8F%89%E7%86%B5%E4%BD%9C%E4%B8%BA%E5%88%86%E7%B1%BB%E9%97%AE%E9%A2%98%E7%9A%84%E6%8D%9F%E5%A4%B1%E5%87%BD%E6%95%B0/D%230012.md)

[D#0013-深度学习调参常用方法总结](https://github.com/Captain1986/CaptainBlackboard/blob/master/D%230013-%E6%B7%B1%E5%BA%A6%E5%AD%A6%E4%B9%A0%E8%B0%83%E5%8F%82%E5%B8%B8%E7%94%A8%E6%96%B9%E6%B3%95%E6%80%BB%E7%BB%93/D%230013.md)

[D#0014-数据降维常用方法总结(LDA,PCA)](https://github.com/Captain1986/CaptainBlackboard/blob/master/D%230014-%E6%95%B0%E6%8D%AE%E9%99%8D%E7%BB%B4%E5%B8%B8%E7%94%A8%E6%96%B9%E6%B3%95%E6%80%BB%E7%BB%93(LDA%2CPCA)/D%230014.md)

[D#0015-深度学习常用损失函数](https://github.com/Captain1986/CaptainBlackboard/blob/master/D%230015-%E6%B7%B1%E5%BA%A6%E5%AD%A6%E4%B9%A0%E5%B8%B8%E7%94%A8%E6%8D%9F%E5%A4%B1%E5%87%BD%E6%95%B0/D%230015.md)

[D#0016-深度学习中不平衡样本的处理](https://github.com/Captain1986/CaptainBlackboard/blob/master/D%230016-%E6%B7%B1%E5%BA%A6%E5%AD%A6%E4%B9%A0%E4%B8%AD%E4%B8%8D%E5%B9%B3%E8%A1%A1%E6%A0%B7%E6%9C%AC%E7%9A%84%E5%A4%84%E7%90%86/D%230016.md)

[D#0017-MTCNN和FaceBoxes](https://github.com/Captain1986/CaptainBlackboard/blob/master/D%230017-MTCNN%E5%92%8CFaceBoxes/D%230017.md)

[D#0019-DeepID1,DeepID2,DeepID2+和DeepID3](https://github.com/Captain1986/CaptainBlackboard/blob/master/D%230019-DeepID1%2CDeepID2%2CDeepID2%2B%E5%92%8CDeepID3/D%230019.md)

[D#0020-Batch-Normalization层原理与分析](https://github.com/Captain1986/CaptainBlackboard/blob/master/D%230020-Batch-Normalization%E5%B1%82%E5%8E%9F%E7%90%86%E4%B8%8E%E5%88%86%E6%9E%90/D%230020.md)

[D#0021-机器学习中的过拟合及其解决办法](https://github.com/Captain1986/CaptainBlackboard/blob/master/D%230021-%E6%9C%BA%E5%99%A8%E5%AD%A6%E4%B9%A0%E4%B8%AD%E7%9A%84%E8%BF%87%E6%8B%9F%E5%90%88%E5%8F%8A%E5%85%B6%E8%A7%A3%E5%86%B3%E5%8A%9E%E6%B3%95/D%230021.md)

[D#0023-CNN模型计算量估计](https://github.com/Captain1986/CaptainBlackboard/blob/master/D%230023-CNN%E6%A8%A1%E5%9E%8B%E8%AE%A1%E7%AE%97%E9%87%8F%E4%BC%B0%E8%AE%A1/D%230023.md)

[D#0024-CNN模型内存访问估计](https://github.com/Captain1986/CaptainBlackboard/blob/master/D%230024-CNN%E6%A8%A1%E5%9E%8B%E5%86%85%E5%AD%98%E8%AE%BF%E9%97%AE%E4%BC%B0%E8%AE%A1/D%230024.md)

[D#0025-CNN中使用卷积代替全连接](https://github.com/Captain1986/CaptainBlackboard/blob/master/D%230025-CNN%E4%B8%AD%E4%BD%BF%E7%94%A8%E5%8D%B7%E7%A7%AF%E4%BB%A3%E6%9B%BF%E5%85%A8%E8%BF%9E%E6%8E%A5/D%230025.md)

[D#0026-深度学习检测小目标常用方法](https://github.com/Captain1986/CaptainBlackboard/blob/master/D%230026-%E6%B7%B1%E5%BA%A6%E5%AD%A6%E4%B9%A0%E6%A3%80%E6%B5%8B%E5%B0%8F%E7%9B%AE%E6%A0%87%E5%B8%B8%E7%94%A8%E6%96%B9%E6%B3%95/D%230026.md)

[D#0027-聊聊2017 ImageNet夺冠的SENet](https://github.com/Captain1986/CaptainBlackboard/blob/master/D%230027-%E8%81%8A%E8%81%8A2017%20ImageNet%E5%A4%BA%E5%86%A0%E7%9A%84SENet/D%230027.md)

[D#0028-再聊SENet的孪生兄弟SKNet](https://github.com/Captain1986/CaptainBlackboard/blob/master/D%230028-%E5%86%8D%E8%81%8ASENet%E7%9A%84%E5%AD%AA%E7%94%9F%E5%85%84%E5%BC%9FSKNet/D%230028.md)

[D#0029-CV中的注意力机制](https://github.com/Captain1986/CaptainBlackboard/blob/master/D%230029-CV%E4%B8%AD%E7%9A%84%E6%B3%A8%E6%84%8F%E5%8A%9B%E6%9C%BA%E5%88%B6/D%230029.md)

[D#0030-类MTCNN的360RIP人脸检测器PCN](https://github.com/Captain1986/CaptainBlackboard/blob/master/D%230030-%E7%B1%BBMTCNN%E7%9A%84360RIP%E4%BA%BA%E8%84%B8%E6%A3%80%E6%B5%8B%E5%99%A8PCN/D%230030.md)

[D#0031-知识蒸馏Knowledge-Distillation](https://github.com/Captain1986/CaptainBlackboard/blob/master/D%230031-%E7%9F%A5%E8%AF%86%E8%92%B8%E9%A6%8FKnowledge-Distillation/D%230031.md)

[D#0032-CNN可视化之类激活热力图Grad-CAM](https://github.com/Captain1986/CaptainBlackboard/blob/master/D%230032-CNN%E5%8F%AF%E8%A7%86%E5%8C%96%E4%B9%8B%E7%B1%BB%E6%BF%80%E6%B4%BB%E7%83%AD%E5%8A%9B%E5%9B%BEGrad-CAM/D%230032.md)

[D#0033-一些分类网络的训练技巧](https://github.com/Captain1986/CaptainBlackboard/blob/master/D%230033-%E4%B8%80%E4%BA%9B%E5%88%86%E7%B1%BB%E7%BD%91%E7%BB%9C%E7%9A%84%E8%AE%AD%E7%BB%83%E6%8A%80%E5%B7%A7/D%230033.md)

[D#0034-火箭发射：阿里巴巴的轻量网络训练方法](https://github.com/Captain1986/CaptainBlackboard/blob/master/D%230034-%E7%81%AB%E7%AE%AD%E5%8F%91%E5%B0%84%EF%BC%9A%E9%98%BF%E9%87%8C%E5%B7%B4%E5%B7%B4%E7%9A%84%E8%BD%BB%E9%87%8F%E7%BD%91%E7%BB%9C%E8%AE%AD%E7%BB%83%E6%96%B9%E6%B3%95/D%230034.md)

[D#0035-2KW短视频打标问题之Activate-Learning](https://github.com/Captain1986/CaptainBlackboard/blob/master/D%230035-2KW%E7%9F%AD%E8%A7%86%E9%A2%91%E6%89%93%E6%A0%87%E9%97%AE%E9%A2%98%E4%B9%8BActivate-Learning/D%230035.md)

[D#0036-2KW短视频打标问题之Multi-Modal-Machine-Learning](https://github.com/Captain1986/CaptainBlackboard/blob/master/D%230036-2KW%E7%9F%AD%E8%A7%86%E9%A2%91%E6%89%93%E6%A0%87%E9%97%AE%E9%A2%98%E4%B9%8BMulti-Modal-Machine-Learning/D%230036.md)

[D#0037-CentralNet做多模态融合](https://github.com/Captain1986/CaptainBlackboard/blob/master/D%230037-CentralNet%E5%81%9A%E5%A4%9A%E6%A8%A1%E6%80%81%E8%9E%8D%E5%90%88/D%230037.md)

[D#0038-Multi-View-Active-Learning做视频推荐](https://github.com/Captain1986/CaptainBlackboard/blob/master/D%230038-Multi-View-Active-Learning%E5%81%9A%E8%A7%86%E9%A2%91%E6%8E%A8%E8%8D%90/D%230038.md)

[D#0039-用FCN做分割](https://github.com/Captain1986/CaptainBlackboard/blob/master/D%230039-%E7%94%A8FCN%E5%81%9A%E5%88%86%E5%89%B2/D%230039.md)

[D#0040-用U-Net做分割](https://github.com/Captain1986/CaptainBlackboard/blob/master/D%230040-用U-Net做分割/D%230040.md)

[D#0041-用RefineNet做分割](https://github.com/Captain1986/CaptainBlackboard/blob/master/D%230041-用RefineNet做分割/D%230041.md)

[D#0042-用DeepLabv3+的Encoder-Decoder做分割](https://github.com/Captain1986/CaptainBlackboard/blob/master/D%230042-%E7%94%A8DeepLabv3%2B%E7%9A%84Encoder-Decoder%E5%81%9A%E5%88%86%E5%89%B2/D%230042.md)

[D#0043-用HRNet做分割](https://github.com/Captain1986/CaptainBlackboard/blob/master/D%230043-%E7%94%A8HRNet%E5%81%9A%E5%88%86%E5%89%B2/D%230043.md)

[D#0044-用Network-Slimming做模型加速和压缩](https://github.com/Captain1986/CaptainBlackboard/blob/master/D%230044-%E7%94%A8Network-Slimming%E5%81%9A%E6%A8%A1%E5%9E%8B%E5%8A%A0%E9%80%9F%E5%92%8C%E5%8E%8B%E7%BC%A9/D%230044.md)

[D#0045-Stacked-Hourglass-Network-for-Human-Pose-Estimation](https://github.com/Captain1986/CaptainBlackboard/blob/master/D%230045-Stacked-Hourglass-Network-for-Human-Pose-Estimation/D%230045.md)

[D#0046-Anchor-Free第一篇CornerNet-Detecting-Objects-as-Paired-Keypoints](https://github.com/Captain1986/CaptainBlackboard/blob/master/D%230046-Anchor-Free%E7%AC%AC%E4%B8%80%E7%AF%87CornerNet-Detecting-Objects-as-Paired-Keypoints/D%230046.md)

[D#0047-Anchor-Free第二篇CornerNet的变种ExtremeNet](https://github.com/Captain1986/CaptainBlackboard/blob/master/D%230047-Anchor-Free%E7%AC%AC%E4%BA%8C%E7%AF%87CornerNet%E7%9A%84%E5%8F%98%E7%A7%8DExtremeNet/D%230047.md)

[D#0048-Anchor-Free第三篇Objects-as-Points](https://github.com/Captain1986/CaptainBlackboard/blob/master/D%230048-Anchor-Free%E7%AC%AC%E4%B8%89%E7%AF%87Objects-as-Points/D%230048.md)

[D#0049-Anchor-Free第四篇CenterNet-Keypoint-Triplets-for-Object-Detection](https://github.com/Captain1986/CaptainBlackboard/blob/master/D%230049-Anchor-Free%E7%AC%AC%E5%9B%9B%E7%AF%87CenterNet-Keypoint-Triplets-for-Object-Detection/D%230049.md)

## 关于Issues

Issues里面我记录了一些自己要写的内容清单，写完一个就Close一个

## 转载须知

**如需转载，请著名原作者“船长”和原文链接**